无需训练即可还原文本嵌入，快速高效且通用。
Universal Zero-shot Embedding Inversion
- 基于对抗解码技术实现零样本文本还原
- 仅需少量查询即可恢复关键语义信息
- 适用于任意文本嵌入，无需定制模型
嵌入反演（Embedding inversion）即在仅有黑盒嵌入编码器访问权限的前提下，根据文本嵌入重建原始文本，是自然语言处理与安全领域的重要问题。从NLP角度看，它揭示了嵌入中保留的输入语义信息量；从安全角度，则衡量向量数据库和基于嵌入的检索系统的信息泄露程度。现有方法如vec2text虽精度高，但需为每个嵌入训练独立模型，且需大量查询编码器。我们提出ZSInvert，一种基于最新对抗解码技术的零样本反演方法。该方法快速、查询高效，可直接应用于任意文本嵌入而无需训练专属反演模型。我们在多个嵌入上评估了ZSInvert的有效性，结果表明其能成功恢复对应文本的关键语义信息。
原文摘要 · Abstract (English)
Embedding inversion, i.e., reconstructing text given its embedding and black-box access to the embedding encoder, is a fundamental problem in both NLP and security. From the NLP perspective, it helps determine how much semantic information about the input is retained in the embedding. From the security perspective, it measures how much information is leaked by vector databases and embedding-based retrieval systems. State-of-the-art methods for embedding inversion, such as vec2text, have high accuracy but require (a) training a separate model for each embedding, and (b) a large number of queries to the corresponding encoder. We design, implement, and evaluate ZSInvert, a zero-shot inversion method based on the recently proposed adversarial decoding technique. ZSInvert is fast, query-efficient, and can be used for any text embedding without training an embedding-specific inversion model. We measure the effectiveness of ZSInvert on several embeddings and demonstrate that it recovers key semantic information about the corresponding texts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。